Semantic Segmentation in Aerial/Satellite imagery

Project Green-Roof: Estimating roof greenification potential from satellite/aerial imagery

Stack:

     
Dr. Markus Meingast ©2019

The Questions

  • What is semantic segmentation?
  • What is it used for?
  • How much $m^2$ of roof area is there in Berlin?
  • How much of that area is greened?
  • What potential is there?

Senate Department for Urban Development and Housing (2017)

Roof-top Segmentation

AIRS-Dataset

  • 475km2 of aerial imagery (Auckland, NZ)
  • 7.5cm/px resolution $\rightarrow$ downsampled to 30cm/px
  • 850 images
  • random brightness and zoom augmentation

U-Net Model

  • Encoder / Decoder type neural net (with skip-connections)
  • 39 layers
  • 2.000.000 parameters
  • heavy lifting done on Google Colab (GPU)

Prediction

raw input
base truth
prediction

Cars Segmentation

In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [8]:
import pandas as pd
from IPython.display import HTML

import matplotlib.pyplot as mp
mp.style.use(['dark_background'])

import numpy as np
import pandas as pd

import plotly as pl
import plotly.graph_objects as go

import plotly.express as px

import ee

Heading Nr. 2

Some random text

Altair Plots (working with IFrame import)

Out[13]:

Plotly Plot